Documentation

System One

POST/v1/systemone

Answers a TypeSafe System One request (model jev-1.13.0). Both catalog tags jev and typesafe-systemone use this single path.

Start

Help

Python Setup

Node.js Setup

PHP Setup

API Reference

Request body

model

required — jev-1.13.0

state

required — current game or decision state, forwarded unchanged

questions

required — map of noul, choice and score questions

cURL example

terminal

curl https://apily.pro/v1/systemone \
  -H "Authorization: Bearer apily_your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"jev-1.13.0","state":{"board":"start"},"questions":{"noul":"what next","choice":"hold or raise","score":0.4}}'

Error responses

Symptom	Cause	Fix
`401 Missing API key`	No auth header was sent.	Apily accepts `Authorization: Bearer …` and `x-api-key: …`.
`401 Invalid API key`	Key copied with stray spaces, truncated, or revoked.	Copy the key whole from the API page in your Apily account, the `apily_` prefix included.
`403 Email not verified`	Your Apily account's email address isn't verified yet.	Verify your email from the banner in the Apily app, then retry.
`404 Model not found`	The model ID isn't in the Apily catalog.	Copy the exact ID from `GET /v1/models` or the Models page in your account.
`503 Model temporarily unavailable`	The model exists, but no upstream provider is reachable right now.	Retry in a moment — it usually recovers within a minute. Switch models if it keeps happening.
`402 Insufficient balance`	Your token balance can't cover the request's estimated cost.	Top up your balance on the Billing page in your Apily account.
`429 Too many requests`	Your account sent more than 600 `/v1/*` requests in a minute — all of your API keys share one budget. The body is `{ error: { message, type: "rate_limit_error", code: "rate_limit_exceeded" }, retryAfterSeconds }`.	Wait the `Retry-After` header (or `retryAfterSeconds`) before retrying, and lower request concurrency.
`502 Upstream error`	The upstream provider returned an unexpected error.	Retry the request; try a different model if it persists.

Billed by usage.input_tokens (or usage.prompt_tokens) at the model's input price. Output tokens are recorded but not charged. If the provider returns no usage, the reserved estimate of state and questions is billed.